Of the 182 identified genera of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 153 of the genera
In the vast majority of cases, Random Forest models appeared to train the best predictive models based on RMSE values.
| BestModel_RMSE | Number of Genera |
|---|---|
| RF | 93 |
| RPART | 22 |
| BAGEARTH | 11 |
| GBM | 11 |
| RPART2 | 5 |
| TREEBAG | 5 |
| XGBOOST | 3 |
| GLM | 2 |
| GBM,RPART | 1 |
We were able to attain R-squared values of >= 0.2 for 28% of the trained genera models.
R-squared values plotted according to sample size
Data summary of trained models.
Of the 593 identified species of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 240 of the species.
In the vast majority of cases, Random Forest models appeared to train the best predictive models based on RMSE values.
| BestModel_RMSE | Number of Species |
|---|---|
| RF | 126 |
| RPART | 35 |
| BAGEARTH | 19 |
| GBM | 19 |
| XGBOOST | 14 |
| TREEBAG | 11 |
| LM | 9 |
| GLM | 4 |
| RPART2 | 3 |
We were able to attain R-squared values of >= 0.2 for 21% of the trained species models.
R-squared values plotted according to sample size
Data summary of trained models.
Of the 216 identified subspecies of importance for deer and elk forage or sage-grouse, we had sufficient data (e.g. at least 3 ecognition polygons) to train models for 11 of the subspecies.
| BestModel_RMSE | Number of Subspecies |
|---|---|
| RF | 6 |
| GBM | 2 |
| TREEBAG | 2 |
| RPART | 1 |
We were able to attain R-squared values of >= 0.2 for 64% of the trained subspecies models.
R-squared values plotted according to sample size
Data summary of trained models.